Intelligent Machines Lab Reading Group

The Intelligent Machines Lab Reading Group meets every Friday at 11:00 A.M. (tentative) in LT-5, Level 6 (tentative) at Information Technology University, Lahore. We present and discuss publications, tools and experiments from variety of areas like Computer Vision, Deep Learning, Machine Learning, Robotics, Human Object Interaction and Geographic Information System (GIS). These meetings are very informal, everyone (faculty members, students, research fellows etc.) is welcomed to join us. Our objective is to provide venue for sharing new developments, enhance mathematical rigor and have fun helping each other.

Organizers: Mr. Javed Iqbal & Mr. Muhammad Akhtar Munir

Please email at and if you would like to present a paper at the group.

Upcoming Presentations

Date Presenter Paper or topic
June 18, 2021 Sohail Danish An Image is Worth 16×16 Words: Transformers for Image Recognition at Scale [pdf]
Authors: Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby

Previous Presentations

Date Presenter Paper or topic
March 13th, 2020 Nadeem Yousaf Ablation-CAM: Visual Explanations for Deep Convolutional Network via Gradient-free Localization [pdf]
Authors: Saurabh Desai, Harish G. Ramaswamy
March 6th, 2020 Mehwish Ghafoor A General and Adaptive Robust Loss Function [pdf]
Authors: Jonathan T. Barron
Feb 28th, 2020 Hira Yaseen Videos as Space-Time Region Graphs [pdf]
Authors: Xiaolong Wang, Abhinav Gupta
Feb 21st, 2020 Muhammad Momin Stacked Capsule Autoencoders [pdf]
Authors: Adam R. Kosiorek, Sara Sabour, Yee Whye Teh, Geoffrey E. Hinton
Feb 14th, 2020 Zoya Naseer Hashmi Deformable Convolutional Networks [pdf]
Authors: Jifeng Dai, Haozhi Qi, Yuwen Xiong, Yi Li, Guodong Zhang, Han Hu, Yichen Wei
Aug 17th, 2018 Anza Shakeel Fully Convolutional Crowd Counting On Highly Congested Scenes[pdf]
Authors: Mark Marsden, Kevin McGuinness, Suzanne Little and Noel E. O’Connor
Oct 19th, 2018 Jawad Mansoor Hyperspherical Variational Autoencoder[pdf]
Authors: Tim R. Davidson, Luca Falorsi, Nicola De Cao, Thomas Kipf, Jakub M. Tomczak
Aug 10th, 2018 Javed Iqbal People, Penguins and Petri Dishes: Adapting Object Counting Models To New Visual Domains And Object Types Without Forgetting [pdf]
Authors: Mark Marsden, Kevin McGuinness, Suzanne Little, Ciara E. Keogh and Noel E. O’Connor
May 11th, 2018 Dr. Amara Tariq Automatic image annotation systems
May 4th, 2018 Sarmad Khitran Generative Adversarial Networks (GANs) for future prediction and their application in anomaly detection [pdf]
Authors: Carl Vondrick and Antonio Torralba
April 27th, 2018 Jawad Mansoor Regular Shapes Detection in Satellite Images [pdf]
Authors: Ahmad Reza Eskandari and Zahra Kouchaki
April 20th, 2018 Amna Gillani Visual Sentiment Ontology [pdf]
Authors: Brendan Jou, Tao Chen, Nikolaos Pappas, Miriam Redi, Mercan Topkara, Shih-Fu Chang
March 30th, 2018 Dr. Waqas Sultani Weakly Labeled Human Action Recognition [pdf]
Authors: Waqas Sultani, Chen Chen, Mubarak Shah
March 16th, 2018 Javed Iqbal Detect to Track and Track to Detect [pdf]
Authors: Christoph Feichtenhofer, Axel Pinz and Andrew Zisserman
March 9th, 2018 Jawad Mansoor Kitti Vission Benchmark [pdf]
Authors: Andreas Geiger and Philip Lenz and Raquel Urtasun
March 2nd, 2018 Muhammad Akhtar Munir SSD: Single Shot Multibox Detector [pdf]
Authors: Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Ber
February 23rd, 2018 Anwar Said CC-GA: A clustering coefficient based genetic algorithm for detecting communities in social networks [pdf]
Authors: Anwar Said, Rabeeh Ayaz Abbasi, Onaiza Maqbool, Ali Daud, Naif Radi Aljohani
February 16th, 2018 Muhammad Faisal Efficient Video Object Segmentation via Network Modulation [pdf]
Authors: Linjie Yang, Yanran Wang, Xuehan Xiong, Jianchao Yang, Aggelos K. Katsaggelos
February 9th, 2018 Muhammad Awais Understanding deep learning requires rethinking generalization [pdf]
Authors: Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, Oriol Vinyals
January 26th, 2018 Hafiz Hassan Saeed Probabilistic Semi-Supervised Multi-Modal Hashing [pdf]
Authors: Behnam Gholami, Abolfazl Hajisami
January 19th, 2018 Javed Iqbal Road lanes and lane lines detection for self driving cars
December 22, 2017 Tabasher Arif You Only Look Once: Unified, Real-Time Object Detection [pdf]
Authors: Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi
December 15, 2017 Muhammad Akhtar Munir Spatial Transformer Networks [pdf]
Authors: Max Jaderberg, Karen Simonyan, Andrew Zisserman, Koray Kavukcuoglu
December 7, 2017 Muhammad Usama Issues in CNN design and Capsule Networks [pdf]
Authors: Sara Sabour, Nicholas Frosst, Geoffrey E Hinton
October 20, 2017 Dr. Mohsen Ali Finding Tiny Faces [pdf]
Authors: Peiyun Hu, Deva Ramanan
October 13, 2017 Ruhan Asghar Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action Recognition [pdf]
Authors: Junwu Weng, Chaoqun Weng, Junsong Yuan
October 6, 2017 Tehreem Aslam Superpixel-based Color Transfer [pdf]
Authors: RĀ“emi Giraud, Vinh-Thong Ta, Nicolas Papadakis
September 29, 2017 Mohsin Riaz SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size [pdf]
Authors: Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, Kurt Keutzer
Sep 22, 2017 Rabia Rafique Active Learning Tutorial
Sep 22, 2017 Javed Iqbal Introduction to Reinforcement Learning
August 25, 2017 Mohsin Riaz Design of an Energy-Efficient Accelerator for Training of Convolutional Neural Networks using Frequency-Domain Computation [pdf]
Authors: Jong Hwan Ko, Burhan Mudassar, Taesik Na, and Saibal Mukhopadhyay. Design Automation Conference, – 2017
August 18, 2017 Afsheen Rafaqat Ali Emotion Recognition in Context [pdf]
Authors: Ronak Kosti, Jose M. Alvarez, Adria Recasens, Agata Lapedriza, CVPR – 2017
August 11, 2017 Dr. Mudassir Shabbir Introduction to VC Dimesions
August 3, 2017 Anza Shakeel Multi-Scale Dense Convolutional Networks for Efficient Prediction [pdf]
Authors: Gao Huang(Cornell University), Danlu Chen(Fudan University), Tianhong Li (Tsinghua University), Felix Wu (Cornell University), Arxiv Paper 2017
July 28, 2017 Mohsen Ali Densely Connected Convolutional Networks [pdf]
Authors: Gao Huang, Zhuang Liu, Kilian Q. Weinberger, Laurens van der Maaten
Published in Conference on Computer Vision and Pattern Recognition, 2017 and received best paper award.
June 22, 2017 Afsheen Rafaqat Ali Is Faster R-CNN Doing Well for Pedestrian Detection? [pdf]
Authors: Liliang Zhang, Liang Lin, Xiaodan Liang, Kaiming He
Published in European Conference on Computer Vision, 2016.
June 9, 2017 Muhammad Nawaz Program sketching [pdf]
Authors: Armando Solar-Lezama
Published in International Journal on Software Tools for Technology Transfer, 2013.
June 2, 2017 Dr. Mohsen Ali Learning Deep Features for Discriminative Localization [pdf]
Authors: Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba
Published in Conference on Computer Vision and Pattern Recognition, 2016.
May 26, 2017 Muhammad Athar
Towards Robot Autonomy in Group Conversations: Understanding the Effects of Body Orientation and Gaze [pdf]
Authors: Marynel Vazquez, Elizabeth J. Carter, Braden McDorman, Jodi Forlizzi, Aaron Steinfeld, Scott Hudson
Published in March, 2017 in ACM/IEEE International Conference on Human-Robot Interaction, Vienna, Austria.
May 19, 2017 Muhammad Usama Human-level control through deep reinforcement learning [pdf]
Authors: Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg & Demis HassabisPublished on 25 February 2015 in Nature
May 12, 2017 Afsheen Rafaqat Ali Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks [pdf]
Authors: Jun-Yan Zhu, Taesung Park, Phillip Isola, Alexei A. Efros
Submitted to ICCV 2017
May 5, 2017 Tehreem Aslam Scribbler: Controlling Deep Image Synthesis with Sketch and Color [pdf]
Authors: Patsorn Sangkloy, Jingwan Lu, Chen Fang, Fisher Yu, James Hays
Computer Vision and Pattern Recognition, CVPR 2017
April 28, 2017 Muhammad Faisal and
Sanaullah Manzoor
LipNet: End-To-End Sentence Level Lipreading [pdf]
Authors: Yannis M. Assael, Brendan Shillingford, Shimon Whiteson, Nando de Freitas
Arxiv Paper
April 21, 2017 Anza Shakeel Unsupervised Visual Representation Learning By Context Prediction [pdf]
Authors: Carl Doersch, Abhinav Gupta, Alexei A. Efros
Oral paper at ICCV 2015
April 21, 2017 Umair Shoaib UberNet: Training a ‘Universal’ Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory [pdf]
Author: Iasonas Kokkinos
Arxiv Paper